indosum-seq_bn-rf64-0

This model is a fine-tuned version of LazarusNLP/IndoNanoT5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5046
• Rouge1: 72.7451
• Rouge2: 65.6426
• Rougel: 69.7965
• Rougelsum: 71.8443
• Gen Len: 103.1187

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.001
• train_batch_size: 16
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.8386	1.0	892	0.5658	68.0586	60.6185	65.0879	67.0846	102.556
0.646	2.0	1784	0.5346	69.6096	62.3885	66.6327	68.7343	107.088
0.6031	3.0	2676	0.5019	70.498	63.0668	67.3204	69.5075	101.6693
0.5753	4.0	3568	0.5093	71.6759	64.4776	68.7095	70.7692	104.52
0.5551	5.0	4460	0.5046	72.0617	64.9137	69.0991	71.1205	102.5733

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1